[论文] SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisi...

论文概要

研究领域: NLP 作者: Yasheng Sun, Zezi Zeng, Yifan Yang, Chong Luo, Wenyi Wang, Ziwei Liu, Jürgen Schmidhuber 发布时间: 2026-07-16 arXiv: 2607.15272

中文摘要

编辑论文中的图表是日常研究实践中常规且耗时的工作：作者在修改稿件时重新标注组件、重新排列面板和重新设计视觉样式。然而，在自然语言指令下自动化这一编辑工作流具有挑战性，因为科学图表是一种密集的信息图，其中示意图、图表、照片、标题和箭头等各类异构视觉元素在严格的视觉语法下组合以推进特定论点。为解决这一问题，我们提出SciDiagramEdit，一个从自然论文修订中学习的基准和技能进化框架，它在图表的可编辑矢量源上操作，用户可以检查并与智能体共同编辑各个图元。我们的基准从arXiv版本历史中提取修订前后的图表对，每对图表都锚定在作者自己的修订意图上。为适应编辑指令的多样性，我们采用基于技能进化的智能体学习：一个智能体提议者持续根据多轮执行轨迹优化智能体的技能规范。生成的技能在验证集上逐步提升编辑准确率，证明自然论文修订是指令驱动图表编辑的有效训练信号。

原文摘要

Editing the figures in a research paper is a routine and time-consuming part of everyday research practice: authors relabel components, rearrange panels, and restyle visuals as they revise their manuscripts. Automating this editing workflow under a natural-language instruction, however, is challenging, because a scientific figure is a dense infographic in which heterogeneous visual elements such as schematics, plots, photos, captions, and arrows are composed under a tight visual grammar to advance a specific argument. To address this, we present SciDiagramEdit, a benchmark and skill-evolution framework that learns from natural paper revisions and operates on the figure's editable vector source, where users can inspect and co-edit individual primitives alongside the agent. Our benchmark min...

--- *自动采集于 2026-07-18*

#论文 #arXiv #NLP #小凯